一次训练，任意部署：面向多模态推荐的 Matryoshka 表示学习
Train Once, Deploy Anywhere: Matryoshka Representation Learning for Multimodal Recommendation
AI总结：
针对多模态序列推荐中自适应、高效部署的难题，提出 fMRLRec 框架，通过对齐映射、线性嵌套特征和状态空间建模实现一次训练生成多粒度模型，并在多个基准上优于现有方法。
摘要：
尽管语言和视觉建模近期取得了进展，但将丰富的多模态知识整合到推荐系统中仍面临重大挑战。这主要源于高效推荐的需求，即系统必须具备自适应和交互式响应能力。在本研究中，我们聚焦序列推荐，提出了一个轻量级框架，称为面向多模态推荐的全尺度 Matryoshka 表示学习（fMRLRec）。我们的 fMRLRec 捕获不同粒度的物品特征，学习信息丰富的表示，以在多个维度上实现高效推荐。为整合来自不同模态的物品特征，fMRLRec 采用简单映射，将多模态物品特征投影到对齐的特征空间中。此外，我们设计了一种高效的线性变换，将较小的特征嵌入到较大的特征中，从而显著降低在推荐数据上进行大规模训练所需的内存。结合改进的状态空间建模技术，fMRLRec 可扩展到不同维度，并且只需一次训练即可生成适配各种粒度的多个模型。我们在多个基准数据集上证明了 fMRLRec 的有效性和效率，其性能始终优于最先进的基线方法。我们在 https://github.com/yueqirex/fMRLRec 公开了代码和数据。
英文摘要：
Despite recent advancements in language and vision modeling, integrating rich multimodal knowledge into recommender systems continues to pose significant challenges. This is primarily due to the need for efficient recommendation, which requires adaptive and interactive responses. In this study, we focus on sequential recommendation and introduce a lightweight framework called full-scale Matryoshka representation learning for multimodal recommendation (fMRLRec). Our fMRLRec captures item features at different granularities, learning informative representations for efficient recommendation across multiple dimensions. To integrate item features from diverse modalities, fMRLRec employs a simple mapping to project multimodal item features into an aligned feature space. Additionally, we design an efficient linear transformation that embeds smaller features into larger ones, substantially reducing memory requirements for large-scale training on recommendation data. Combined with improved state space modeling techniques, fMRLRec scales to different dimensions and only requires one-time training to produce multiple models tailored to various granularities. We demonstrate the effectiveness and efficiency of fMRLRec on multiple benchmark datasets, which consistently achieves superior performance over state-of-the-art baseline methods. We make our code and data publicly available at https://github.com/yueqirex/fMRLRec.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
